Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
An MCP (Model Context Protocol) server that acts as a bridge to query multiple LLMs -- both OpenAI-compatible HTTP APIs and CLI coding agents. Just like rubber duck debugging, explain your problems to various AI "ducks" and get different perspectives! Universal OpenAI Compatibility -- Works with any OpenAI-compatible API endpoint CLI Agent Support -- Use CLI coding agents (Claude Code, Codex,…
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
architectureNo description publishedThis tool published no description. Forge does not invent one.
designNo description publishedThis tool published no description. Forge does not invent one.
workloadsNo description publishedThis tool published no description. Forge does not invent one.
prioritiesNo description publishedThis tool published no description. Forge does not invent one.
uncertaintiesNo description publishedThis tool published no description. Forge does not invent one.
assumptionsNo description publishedThis tool published no description. Forge does not invent one.
planNo description publishedThis tool published no description. Forge does not invent one.
constraintsNo description publishedThis tool published no description. Forge does not invent one.
concernsNo description publishedThis tool published no description. Forge does not invent one.
blindspotsNo description publishedThis tool published no description. Forge does not invent one.
proposalNo description publishedThis tool published no description. Forge does not invent one.
coveredNo description publishedThis tool published no description. Forge does not invent one.
risk_toleranceNo description publishedThis tool published no description. Forge does not invent one.
diverge_convergeNo description publishedThis tool published no description. Forge does not invent one.
challengeNo description publishedThis tool published no description. Forge does not invent one.
widthNo description publishedThis tool published no description. Forge does not invent one.
convergence_criteriaNo description publishedThis tool published no description. Forge does not invent one.
perspectivesNo description publishedThis tool published no description. Forge does not invent one.
problemNo description publishedThis tool published no description. Forge does not invent one.
contextNo description publishedThis tool published no description. Forge does not invent one.
red_teamNo description publishedThis tool published no description. Forge does not invent one.
targetNo description publishedThis tool published no description. Forge does not invent one.
threat_modelNo description publishedThis tool published no description. Forge does not invent one.
dimensionsNo description publishedThis tool published no description. Forge does not invent one.
reframeNo description publishedThis tool published no description. Forge does not invent one.
stuck_onNo description publishedThis tool published no description. Forge does not invent one.
ask_duckNo description publishedThis tool published no description. Forge does not invent one.
chat_with_duckNo description publishedThis tool published no description. Forge does not invent one.
clear_conversationsNo description publishedThis tool published no description. Forge does not invent one.
list_ducksNo description publishedThis tool published no description. Forge does not invent one.
list_modelsNo description publishedThis tool published no description. Forge does not invent one.
duck_councilNo description publishedThis tool published no description. Forge does not invent one.
duck_judgeNo description publishedThis tool published no description. Forge does not invent one.
get_pending_approvalsNo description publishedThis tool published no description. Forge does not invent one.
approve_mcp_requestNo description publishedThis tool published no description. Forge does not invent one.
mcp_statusNo description publishedThis tool published no description. Forge does not invent one.
tradeoffsNo description publishedThis tool published no description. Forge does not invent one.
optionsNo description publishedThis tool published no description. Forge does not invent one.
criteriaNo description publishedThis tool published no description. Forge does not invent one.
weightsNo description publishedThis tool published no description. Forge does not invent one.
0 of 40 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
An MCP (Model Context Protocol) server that acts as a bridge to query multiple LLMs -- both OpenAI-compatible HTTP APIs and CLI coding agents. Just like rubber duck debugging, explain your problems to various AI "ducks" and get different perspectives! Universal OpenAI Compatibility -- Works with any OpenAI-compatible API endpoint CLI Agent Support -- Use CLI coding agents (Claude Code, Codex, Gemini CLI, Grok, Aider) as ducks Multiple Ducks -- Configure and query multiple LLM providers…
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This package was last scanned before Forge began storing the resolved tree. The next scan will record it.